Text Classification
Transformers
TensorFlow
distilbert
generated_from_keras_callback
text-embeddings-inference
Instructions to use nikoslefkos/rebert_v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nikoslefkos/rebert_v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="nikoslefkos/rebert_v3")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("nikoslefkos/rebert_v3") model = AutoModelForSequenceClassification.from_pretrained("nikoslefkos/rebert_v3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
a58c3a9
1
Parent(s): 8c97612
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# nikoslefkos/rebert_trex_reformed_v3
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Train Loss: 0.4216
|
| 19 |
- Train Accuracy: 0.8541
|
|
|
|
| 13 |
|
| 14 |
# nikoslefkos/rebert_trex_reformed_v3
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on trex for 250 labels.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Train Loss: 0.4216
|
| 19 |
- Train Accuracy: 0.8541
|